© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2793
    Prev
    Next
    INDEX
    Explanations

    geographic locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     escalada
    -1.25
     fiducia
    -1.19
    (),"
    -1.18
     exercí
    -1.17
     accompanied
    -1.14
     Peruvian
    -1.13
     veřej
    -1.13
    謳
    -1.11
     disposizione
    -1.10
     vasca
    -1.09
    POSITIVE LOGITS
     geographical
    1.85
     geographic
    1.73
     geographically
    1.62
     geography
    1.53
     residents
    1.52
     region
    1.52
     counties
    1.46
     towns
    1.41
     cities
    1.40
     inhabitants
    1.40
    Activations Density 0.092%

    No Known Activations